Real-time 3-D Object Recognition Using Scale Invariant Feature Transform and Stereo Vision

被引：0

作者：

Hsu, Gee-Sern ^{[1
]}

Lin, Chyi-Yeu ^{[1
]}

Wu, Jia-Shan ^{[1
]}

机构：

[1] Natl Taiwan Univ Sci & Technol, Dept Mech Engn, Taipei, Taiwan

来源：

PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOTS AND AGENTS | 2009年

关键词：

Object Recognition; Feature Extraction; Scale Invariant Feature Transform (SIFT); Stereo Vision;

D O I：

暂无

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

Scale Invariant Feature Transform (SIFT) and stereo vision are applied together to recognize objects in real time. This work reports the performance of a GPU (Graphic Processing Unit) based real-time feature detector in capturing the features of 3D objects when the objects undergo rotational and translational motions in cluttered backgrounds. We have compared the performance of the feature detector implemented upon GPU to that upon CPU, and shown that GPU-based solution has substantially outperformed its CPU counterpart.

引用

页码：59 / 64

页数：6

共 12 条

[1]

Andrich G, 2006, ITAL J FOOD SCI, V18, P3

[2]

[Anonymous], P BRIT MACH VIS C

[3]

BROWN M., 2002, BRIT MACHINE VISION, P656

[4]

Gonzalez R.C., 2008, Digital Image Processing, V3rd ed.

[5] Image indexing using color correlograms [J].

Huang, J ;

Kumar, SR ;

Mitra, M ;

Zhu, WJ ;

Zabih, R .

1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :762-768

[6] Distinctive image features from scale-invariant keypoints [J].

Lowe, DG .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) :91-110

[7]

Lowe DG, 2001, PROC CVPR IEEE, P682

[8]

Lowe DG, 1999, Proceedings of the International Conference on Computer Vision-Volume 2-Volume 2, ICCV '99, V2, P1150

[9]

Ma WY, 1998, CONF REC ASILOMAR C, P253, DOI 10.1109/ACSSC.1998.750865

[10]

Singh R, 1997, IEEE INT CONF ROBOT, P1651, DOI 10.1109/ROBOT.1997.614380

← 1 2 →